Using an open model feels surprisingly good

A user reports a surprisingly positive experience using the open-source coding tool opencode with a self-hosted inference endpoint, describing it as freeing and private. The user, who works at Modal, tested the newly launched Kimi K3 model on Modal's managed endpoints for a side project instead of upgrading a Claude or ChatGPT plan. Within five minutes, the user had opencode running on their own Modal endpoint, feeling a sense of ownership and independence from other AI providers.

Using an open model feels surprisingly good I've been using Claude and ChatGPT like the next guy for probably two years now. I've never been a huge "open software" nerd or anything like that. But just now, I got opencode working on my own inference endpoint and... it felt surprisingly good. It feels... freeing, somehow. I own the endpoint, and my data just goes from my laptop to there and back. It feels like it's mine. It's really nice. The motivation for this was that I just got home and wanted to start on a little side project, but I don't have the best Claude or ChatGPT plan for my personal account. I work at Modal https://modal.com , and today we just launched Kimi K3 https://modal.com/library/moonshot/kimi-k3 on managed endpoints, and I know Kimi K3 is supposed to be pretty solid, so instead of upgrading my Claude plan, I wanted to give it a try. I didn't directly contribute to this feature, so I haven't gotten to play with it yet. Within about 5 minutes, I had opencode pointed at my own Modal endpoint and running. Spinning up opencode, I just felt a nice, empty blankness. The best way I can describe it is like opening vim after spinning a bunch of time in a big fancy editor. Or maybe like the tendrils tying me to other providers had been cut, and I could breathe freely. I'm being somewhat dramatic here but not exaggerating that much. It's weird, lol, and unexpected to me, which is why I wanted to write about it.